Libraries

library(rvest)
## Loading required package: xml2
library(tidytext)
library(tm)
## Loading required package: NLP
library(plotly)
## Loading required package: ggplot2
## 
## Attaching package: 'ggplot2'
## The following object is masked from 'package:NLP':
## 
##     annotate
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(knitr)
setwd("C:/Users/perot/Desktop/NTU-CSX4001/Week_6&7&8(Project_1)")

Get Local data

rank = read.csv("RATE.csv",stringsAsFactors=FALSE)
rank$point = 21-rank$排行
url = read.csv("url.csv",stringsAsFactors=FALSE,header = F)
rate = read.csv("feature_rate.csv",stringsAsFactors=FALSE,header = T)

Get feature ranking

`

{r rating,warning=FALSE}

for(i in c(0:19)){ raw <- read_html(url$V1[i]) fea <- html_nodes(raw,“#BH-slave ul:nth-child(1) li”)%>%html_text(raw) per <- html_nodes(raw,“.ACG-persent span”)%>%html_text(raw) rate.i = data.frame(fea,per,stringsAsFactors=FALSE) if(i == 1){ rate = data.frame(rate.i,stringsAsFactors=FALSE) } else{ rate = data.frame(rate,rate.i,stringsAsFactors=FALSE) } } write.csv(rate,“feature_rate.csv”)

`

數據呈現

kable(rank)
排行 作品名稱 類型 製作廠商 發售日期 評分 人氣 point
1 窟窿騎士 動作 Team Cherry 2017/2/24 9.8 155 20
2 Undertale 角色扮演 tobyfox 2015/9/15 9.7 349 19
3 我的世界 其他 Mojang AB 2009/5/17 9.6 11853 18
4 上古卷軸 5：無界天際 角色扮演 Bethesda Game Studios 2011/11/11 9.6 2976 17
5 英雄傳說：碧之軌跡 角色扮演 Falcom 2013/4/12 9.6 2176 16
6 巫師 3：狂獵 角色扮演 CD Projekt RED 2015/5/19 9.6 1671 15
7 Little Busters! 冒險 Visual Art’s/Key 2007/7/27 9.6 776 14
8 CLANNAD 冒險 Key 2004/4/28 9.6 614 13
9 聖靈之光 冒險 Moon Studios GmbH 2015/3/11 9.6 365 12
10 星露谷物語 角色扮演 ConcernedApe 2016/2/27 9.6 359 11
11 Ever17：時光的羈絆（中文版） 冒險 KID 2004/1/8 9.6 284 10
12 幻想之詩 角色扮演 天使遊戲設計團隊 2013/9/6 9.6 267 9
13 魔法使之夜 冒險 Type-Moon 2012/4/12 9.6 261 8
14 RPG 製作大師 MV 其他 Kadokawa Games&Yoji Ojima 2015/10/23 9.6 213 7
15 英雄傳說 空之軌跡 SE 終回特典 角色扮演 Falcom 2011/12/20 9.6 192 6
16 史萊姆農場 策略模擬 Monomi Park 2016/1/15 9.6 132 5
17 鋼鐵雄心 4 策略模擬 Paradox Development Studio 2016/6/6 9.6 130 4
18 恆星戰役 策略模擬 Paradox Development Studio 2016/5/9 9.6 97 3
19 俠盜獵車手 5 動作 Rockstar North 2015/4/14 9.5 9488 2
20 英雄傳說 零之軌跡 角色扮演 Falcom 2011/9/10 9.5 2441 1

遊戲的類別分布

#category
rank.an = rank
rank.an = rank.an %>%  
  group_by(類型) %>%
  summarise(no_rows = length(類型))
plot_ly(rank.an, labels = ~類型,values = ~no_rows, type = 'pie') %>%
  layout(title = '巴哈姆特PC遊戲評分前20類型比例',
         xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
#released date

好遊戲不受時間影響，仍然屹立不搖

plot_ly(rank, x= ~發售日期 ,y= ~point, type = 'scatter',mode="markers",text = ~paste('遊戲名稱: ', 作品名稱))

玩家注重的東西

  cou = c()
  for(i in c(1:20)){
    for(j in rate[[2*i-1]]){
      cou = c(cou,j)
    }
  }

cou= as.factor(cou)

cou = data.frame(cou,c(1:100))

plot_ly(cou ,x= ~cou ,type = 'histogram')
cu = cou %>%  
  group_by(cou) %>%
  summarise(freq = length(cou))
cu = arrange(cu, desc(freq))
plot_ly(cu, labels = ~cou,values = ~freq, type = 'pie') %>%
  layout(title = '巴哈姆特PC遊戲評分前20遊戲特色比例',
         xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
         yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))